This session explores the evolution from simple LLM chains to robust cognitive architectures, focusing on deploying stateful agents within your own perimeter (On-Premise). We will compare modern orchestration frameworks, contrasting Google ADK (Agent Development Kit) for structured, model-agnostic agent design against LangGraph for granular state control and CrewAI for multi-agent role-playing. A key focus will be the Model Context Protocol (MCP) — the new standard for connecting agents to internal data and tools without vendor lock-in. We will demonstrate how to build a flexible runtime using Vercel AI SDK Core (deployed in Docker) to serve these agents, ensuring full independence from cloud providers. Finally, we will cover the AgentOps stack, detailing how to implement self-hosted observability (via Langfuse) and access policies to safely manage autonomous systems in production.

This talk is about a real DevOps project whose journey turned out to be strikingly similar to the storyline of The Phoenix Project. I will walk through the entire path: building the platform, migration, working with development teams, communicating with the business, operating the system under load, and the kinds of mistakes that become visible only over time. This is not a retelling of the book and not a success story. It is a conversation about systemic decisions, responsibility, learning, incident preparedness, and how complex technical systems shape the behavior of the people within them. The talk focuses not on tools, but on the insights that appear only when a project is lived from start to finish — from an idea to the reality of production.

Updating core dependencies is often postponed for years due to the fear of “breaking everything,” causing the risk to grow exponentially. Andrii will present a workflow for jumping across multiple versions: AI analyzes breaking changes and generates transformation rules, AST-based tools handle the routine work, and technical debt becomes a manageable process.

Low Latency in High-Load Systems: From Redis Pub/Sub to In-Memory Runtime — a Toy That Went Too Far In this talk, we will explore real-world experience in building a low-latency system for cross-exchange operations, where geography is just as important as algorithms. We will discuss why message brokers and classic microservices are not a good fit for HFT (High-Frequency Trading)-like scenarios, how in-memory state combined with regional runtime nodes provides predictable latency, and where the boundary lies between speed and consistency.

Team and service growth often leads to a situation where each individual decision seems right, but the system as a whole becomes complex, unpredictable, and difficult to maintain. In this talk, the speaker will explain how they and their team approached technology standardization, what they decided to unify versus what they intentionally left to team ownership, and why observability became not a goal, but a natural outcome of this approach.

When a system consists of dozens of independent repositories, a classic monorepo is not always the right fit. Dmytro will explain how a meta-repo built with Git submodules and AI-powered tools makes it possible to preserve service autonomy while working with them as a single ecosystem. You will see real-world scenarios where AI: • connects code, contracts, and documentation • assists with automated testing and integrations • simplifies collaboration for developers, QA, and product teams • accelerates prototyping and delivery

Knowing SOLID and the GoF patterns is like knowing the traffic rules: you can pass the exam and still crash your car. There’s a huge gap between “I know the Single Responsibility Principle exists” and “I understand why it matters right here.” In that gap live God objects, irreplaceable dependencies, and interfaces no one can actually implement. Using real mistakes from a large-scale project, we’ll explore the difference between knowledge and understanding, how frameworks can hide architectural issues, and why the only way to write maintainable code is to understand the “why,” not just memorize the “how.”

Turbo-guide to the hottest Chrome DevTools updates for 2024–2025 that radically transform the frontend development workflow. We will dive into the integration of Gemini AI, which now acts as your personal super-analyst inside the Performance Panel. Beyond AI, we will explore enhanced performance analysis with expanded Core Web Vitals support and calibrated CPU throttling presets, helping you turn the battle with the “slippery” LCP into a clear detective-style investigation. Along with hardcore debugging, we will cover new styling and usability features such as scroll-driven animations and improved work with CSS Nesting, Autofill, and many other perks. We’ll take a closer look at MCP, because if you don’t know what MCP is — you won’t get paid in 2026.

Everyone has already heard about web accessibility — but following it is not just about good contrast or having alternative text. Learn how to make your digital product truly accessible and avoid common mistakes at the meetup.